Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code, error, while, direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    குதி
    0.42
     Herbert
    0.38
     Megan
    0.38
    Louis
    0.38
     Hodges
    0.37
     Lead
    0.36
    Herbert
    0.36
     Preto
    0.36
     Dup
    0.35
    რი
    0.35
    POSITIVE LOGITS
    ドー
    0.38
    leyin
    0.37
     imprison
    0.37
    ğmen
    0.37
    ildiği
    0.36
    iffent
    0.36
     oxígeno
    0.36
     prü
    0.36
    𐰴
    0.36
     arginine
    0.36
    Act Density 0.000%

    No Known Activations